ionet.json

  1{
  2  "name": "io.net",
  3  "id": "ionet",
  4  "api_key": "$IONET_API_KEY",
  5  "api_endpoint": "https://api.intelligence.io.solutions/api/v1",
  6  "type": "openai-compat",
  7  "default_large_model_id": "moonshotai/Kimi-K2.5",
  8  "default_small_model_id": "zai-org/GLM-4.7-Flash",
  9  "models": [
 10    {
 11      "id": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar",
 12      "name": "Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR",
 13      "cost_per_1m_in": 0.22,
 14      "cost_per_1m_out": 0.95,
 15      "cost_per_1m_in_cached": 0.11,
 16      "cost_per_1m_out_cached": 0.44,
 17      "context_window": 106000,
 18      "default_max_tokens": 10600,
 19      "can_reason": false,
 20      "supports_attachments": false
 21    },
 22    {
 23      "id": "meta-llama/Llama-3.3-70B-Instruct",
 24      "name": "Meta: Llama 3.3 70B Instruct",
 25      "cost_per_1m_in": 0.1,
 26      "cost_per_1m_out": 0.32,
 27      "cost_per_1m_in_cached": 0.05,
 28      "cost_per_1m_out_cached": 0.2,
 29      "context_window": 128000,
 30      "default_max_tokens": 12800,
 31      "can_reason": true,
 32      "reasoning_levels": [
 33        "low",
 34        "medium",
 35        "high"
 36      ],
 37      "default_reasoning_effort": "medium",
 38      "supports_attachments": false
 39    },
 40    {
 41      "id": "MiniMaxAI/MiniMax-M2.5",
 42      "name": "MiniMaxAI/MiniMax-M2.5",
 43      "cost_per_1m_in": 0.195,
 44      "cost_per_1m_out": 1.25,
 45      "cost_per_1m_in_cached": 0.1,
 46      "cost_per_1m_out_cached": 0,
 47      "context_window": 196600,
 48      "default_max_tokens": 19660,
 49      "can_reason": false,
 50      "supports_attachments": false
 51    },
 52    {
 53      "id": "mistralai/Mistral-Large-Instruct-2411",
 54      "name": "Mistral: Mistral Large Instruct 2411",
 55      "cost_per_1m_in": 2,
 56      "cost_per_1m_out": 6,
 57      "cost_per_1m_in_cached": 1,
 58      "cost_per_1m_out_cached": 4,
 59      "context_window": 128000,
 60      "default_max_tokens": 12800,
 61      "can_reason": false,
 62      "supports_attachments": true
 63    },
 64    {
 65      "id": "moonshotai/Kimi-K2-Instruct-0905",
 66      "name": "MoonshotAI: Kimi K2 Instruct 0905",
 67      "cost_per_1m_in": 0.39,
 68      "cost_per_1m_out": 1.9,
 69      "cost_per_1m_in_cached": 0.195,
 70      "cost_per_1m_out_cached": 0.78,
 71      "context_window": 262144,
 72      "default_max_tokens": 26214,
 73      "can_reason": false,
 74      "supports_attachments": false
 75    },
 76    {
 77      "id": "moonshotai/Kimi-K2-Thinking",
 78      "name": "MoonshotAI: Kimi K2 Thinking",
 79      "cost_per_1m_in": 0.32,
 80      "cost_per_1m_out": 0.48,
 81      "cost_per_1m_in_cached": 0.16,
 82      "cost_per_1m_out_cached": 0.64,
 83      "context_window": 262144,
 84      "default_max_tokens": 26214,
 85      "can_reason": true,
 86      "reasoning_levels": [
 87        "low",
 88        "medium",
 89        "high"
 90      ],
 91      "default_reasoning_effort": "medium",
 92      "supports_attachments": false
 93    },
 94    {
 95      "id": "moonshotai/Kimi-K2.5",
 96      "name": "MoonshotAI: Kimi K2.5",
 97      "cost_per_1m_in": 0.445,
 98      "cost_per_1m_out": 2.22,
 99      "cost_per_1m_in_cached": 0.225,
100      "cost_per_1m_out_cached": 1.1,
101      "context_window": 262144,
102      "default_max_tokens": 26214,
103      "can_reason": true,
104      "reasoning_levels": [
105        "low",
106        "medium",
107        "high"
108      ],
109      "default_reasoning_effort": "medium",
110      "supports_attachments": false
111    },
112    {
113      "id": "openai/gpt-oss-120b",
114      "name": "OpenAI: gpt-oss-120b",
115      "cost_per_1m_in": 0.02,
116      "cost_per_1m_out": 0.1,
117      "cost_per_1m_in_cached": 0.01,
118      "cost_per_1m_out_cached": 0.04,
119      "context_window": 131072,
120      "default_max_tokens": 13107,
121      "can_reason": true,
122      "reasoning_levels": [
123        "low",
124        "medium",
125        "high"
126      ],
127      "default_reasoning_effort": "medium",
128      "supports_attachments": false
129    },
130    {
131      "id": "openai/gpt-oss-20b",
132      "name": "OpenAI: gpt-oss-20b",
133      "cost_per_1m_in": 0.016,
134      "cost_per_1m_out": 0.06,
135      "cost_per_1m_in_cached": 0.008,
136      "cost_per_1m_out_cached": 0.032,
137      "context_window": 64000,
138      "default_max_tokens": 6400,
139      "can_reason": true,
140      "reasoning_levels": [
141        "low",
142        "medium",
143        "high"
144      ],
145      "default_reasoning_effort": "medium",
146      "supports_attachments": false
147    },
148    {
149      "id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
150      "name": "Qwen: Qwen3 Next 80B A3B Instruct",
151      "cost_per_1m_in": 0.06,
152      "cost_per_1m_out": 0.6,
153      "cost_per_1m_in_cached": 0.03,
154      "cost_per_1m_out_cached": 0.12,
155      "context_window": 262144,
156      "default_max_tokens": 26214,
157      "can_reason": false,
158      "supports_attachments": false
159    },
160    {
161      "id": "zai-org/GLM-4.6",
162      "name": "Z.ai: GLM 4.6",
163      "cost_per_1m_in": 0.35,
164      "cost_per_1m_out": 1.5,
165      "cost_per_1m_in_cached": 0.175,
166      "cost_per_1m_out_cached": 0.7,
167      "context_window": 200000,
168      "default_max_tokens": 20000,
169      "can_reason": true,
170      "reasoning_levels": [
171        "low",
172        "medium",
173        "high"
174      ],
175      "default_reasoning_effort": "medium",
176      "supports_attachments": false
177    },
178    {
179      "id": "zai-org/GLM-4.7",
180      "name": "Z.ai: GLM 4.7",
181      "cost_per_1m_in": 0.3,
182      "cost_per_1m_out": 1.4,
183      "cost_per_1m_in_cached": 0.15,
184      "cost_per_1m_out_cached": 0.6,
185      "context_window": 202752,
186      "default_max_tokens": 20275,
187      "can_reason": true,
188      "reasoning_levels": [
189        "low",
190        "medium",
191        "high"
192      ],
193      "default_reasoning_effort": "medium",
194      "supports_attachments": false
195    },
196    {
197      "id": "zai-org/GLM-4.7-Flash",
198      "name": "Z.ai: GLM 4.7 Flash",
199      "cost_per_1m_in": 0.07,
200      "cost_per_1m_out": 0.4,
201      "cost_per_1m_in_cached": 0.035,
202      "cost_per_1m_out_cached": 0.14,
203      "context_window": 200000,
204      "default_max_tokens": 20000,
205      "can_reason": true,
206      "reasoning_levels": [
207        "low",
208        "medium",
209        "high"
210      ],
211      "default_reasoning_effort": "medium",
212      "supports_attachments": false
213    },
214    {
215      "id": "zai-org/GLM-5",
216      "name": "Z.ai: GLM 5",
217      "cost_per_1m_in": 1,
218      "cost_per_1m_out": 3,
219      "cost_per_1m_in_cached": 0.5,
220      "cost_per_1m_out_cached": 0,
221      "context_window": 202752,
222      "default_max_tokens": 20275,
223      "can_reason": true,
224      "reasoning_levels": [
225        "low",
226        "medium",
227        "high"
228      ],
229      "default_reasoning_effort": "medium",
230      "supports_attachments": false
231    }
232  ]
233}